CN107610379A - One kind shopping recognition methods and shopping cart identification device - Google Patents

One kind shopping recognition methods and shopping cart identification device Download PDF

Info

Publication number
CN107610379A
CN107610379A CN201710811178.8A CN201710811178A CN107610379A CN 107610379 A CN107610379 A CN 107610379A CN 201710811178 A CN201710811178 A CN 201710811178A CN 107610379 A CN107610379 A CN 107610379A
Authority
CN
China
Prior art keywords
msub
commodity
mrow
image
shopping cart
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710811178.8A
Other languages
Chinese (zh)
Inventor
耿根顺
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Hong Feng Intelligent Technology Co Ltd
Original Assignee
Jiangsu Hong Feng Intelligent Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu Hong Feng Intelligent Technology Co Ltd filed Critical Jiangsu Hong Feng Intelligent Technology Co Ltd
Priority to CN201710811178.8A priority Critical patent/CN107610379A/en
Publication of CN107610379A publication Critical patent/CN107610379A/en
Pending legal-status Critical Current

Links

Landscapes

  • Image Analysis (AREA)

Abstract

A kind of shopping recognition methods provided in an embodiment of the present invention and shopping cart identification device, belong to unmanned supermarket's technical field.The bar code information for the commodity that this method is put into shopping cart by obtaining user, so as to generate shopping list, check whether the type and quantity of user's addition shopping cart commodity are consistent with the commodity on the shopping list by the shopping list, and commodity are inconsistent or add the shopping cart after can reminding user in time by commodity barcode scanning when checking commodity not in the shopping list checking, and self-service barcode scanning is carried out to commodity by the shopping cart and identifies commodity that user specifically thrown into the shopping cart and to dutiable value, so as to carry out real-time counting and checkout.Because of the time waited in line needed for commodity barcode scanning when omitting the commodity for not adding shopping list by effectively being avoided to commodity progress image recognition, and efficiently reducing user's checkout, the shopping efficiency of user is improved, saves personal time.

Description

One kind shopping recognition methods and shopping cart identification device
Technical field
The present invention relates to unmanned supermarket's technical field, is identified in particular to one kind shopping recognition methods and shopping cart Device.
Background technology
Supermarket be people through haunt, be frequently seen customer's queuing checkout before Cash register, and unmanned supermarket can To reduce cashier, make intelligence checkout and patron self-service cash register into.Current self-service POS and Self-help vending machine are increasingly Improve and ripe, not only reduce the time that customer waits in line, also improve the shopping efficiency of customer and the cash register of businessman Efficiency.Life to people brings great convenience.But the self-checkout of current unmanned supermarket, do shopping, pay, How much is paid all to be determined by customer oneself, just left even if customer does not settle accounts, there will not be staff's obstruction.So according to Rely customer sincere and the purchase system flow of consciousness, serious threat the interests of businessman, corrupted social values simultaneously.Uniquely Monitoring device camera also has its limitation, and staff at every moment can not possibly stare at camera, goes observation customer to have It is to take commodity, either with or without few checkout or even either with or without checkout etc. more, even if staff can have found to fail sincerity in time The customer of commodity is paid the bill or appropriates public property for personal use, it is in management and more complicated.So as to also exist in the prior art and customer is chosen The technical problem of identification and the counting of commodity.
The content of the invention
The present invention provides a kind of shopping recognition methods and shopping cart identification device, it is intended to improves above-mentioned technical problem.
A kind of shopping recognition methods provided by the invention, applied to shopping cart identification device, including:Obtain user and be put into purchase The bar code information of the in-car commodity of thing, and generate shopping list;Judge whether to have in the shopping cart and do not scan bar code Commodity;If so, obtain the total price of all commodity in the shopping cart.
Preferably, it is described to judge whether there are the commodity for not scanning bar code in the shopping cart, including:Gather the shopping The image of in-car all commodity;Based on described image, the commodity amount and type of merchandize in the shopping cart are identified;Judge institute State type of merchandize and whether the commodity amount is consistent with the shopping list;If so, judge that the commodity in the shopping cart are equal Bar code is scanned;If it is not, judge there are at least one commodity not scan bar code in the shopping cart.
Preferably, the commodity amount and type of merchandize for being based on described image, identifying in the shopping cart, including:Sentence It is overlapping whether the commodity image in disconnected described image occurs;If so, image point is carried out to described image based on image segmentation algorithm From obtaining separated target image;Obtain the characteristics of image in the target image;Preset based on described image characteristic query Image data base, obtain type of merchandize and commodity amount corresponding to described image feature.
Preferably, it is described that image separation is carried out to described image based on image segmentation algorithm, including:Described image is changed Into gray-scale map;Single stochastic variable based on gray level distributes the intensity level of the pixel of the gray-scale map;Acquisition amplitude is more than 1 Gray level image histogram distribution amplitude threshold, the amplitude threshold meets:Wherein, l0Represent the gray level that amplitude is more than or equal to 1, StRepresent ash Spend level l0The summation of appearance;The self-adapting window width of each gray level image is obtained based on described image histogram, it is described adaptive Window width w is answered to meet:Wherein, ltRepresent that amplitude is more than or equal to threshold value in histogram Amplitude TpGray level sum, α is a constant { α ∈ Z+|1≤α≤lt};Amplitude is obtained based on vertical scanning histogram to be more than All peak values of the amplitude threshold;Based on horizontal sweep histogram to obtain true peak gray level, the true peak ash Spend level lrMeet:Wherein, liExpression belongs to by the window w grey level range r defined gray level Amplitude;Initiation parameter included in gray level and the gray level image based on peak-peak is clustered by K-means Algorithm carries out image separation.
Preferably, it is described if so, obtain the total price of all commodity in the shopping cart, also include before:Work as collection When being reduced to the commodity amount in the shopping cart, judge that user retracts the commodity, and send prompt message.
A kind of shopping cart identification device provided by the invention, including:Data capture unit, shopping is put into for obtaining user The bar code information of in-car commodity, and generate shopping list;Judging unit, do not swept for judging whether to have in the shopping cart Retouch the commodity of bar code;Clearing unit, for if so, obtaining the total price of all commodity in the shopping cart.
Preferably, the judging unit includes:Subelement is gathered, for gathering the figure of all commodity in the shopping cart Picture;Subelement is identified, for based on described image, identifying the commodity amount and type of merchandize in the shopping cart;Judge that son is single Member, for judging whether the type of merchandize and the commodity amount are consistent with the shopping list;First result unit, is used for If so, judge that the commodity in the shopping cart have scanned bar code;Second result unit, for if it is not, judging the purchase Thing in-car has at least one commodity not scan bar code.
Preferably, the identification subelement includes:Judging submodule, for whether judging the commodity image in described image Occur overlapping;Image procossing submodule, for if so, carrying out image separation, acquisition to described image based on image segmentation algorithm Separated target image;Acquisition submodule, for obtaining the characteristics of image in the target image;Submodule is inquired about, is used for Based on described image characteristic query pre-set image database, the type of merchandize and commodity number corresponding to described image feature are obtained Amount.
Preferably, described image processing submodule is specifically used for:Convert the image into gray-scale map;Based on gray level Single stochastic variable distributes the intensity level of the pixel of the gray-scale map;The image histogram of gray level of the acquisition amplitude more than 1 The amplitude threshold of distribution, the amplitude threshold meet:Wherein, l0Represent Amplitude is more than or equal to 1 gray level, StRepresent gray level l0The summation of appearance;Each ash is obtained based on described image histogram The self-adapting window width of image is spent, the self-adapting window width w meets:Wherein, lt Represent that amplitude is more than or equal to threshold amplitude T in histogrampGray level sum, α is a constant { α ∈ Z+|1≤α≤ lt};All peak values of the amplitude more than the amplitude threshold are obtained based on vertical scanning histogram;Based on horizontal sweep histogram with Obtain true peak gray level, the true peak gray level lrMeet:Wherein, liExpression belongs to By the amplitude of the window w grey level range r defined gray level;Institute in gray level and the gray level image based on peak-peak Comprising initiation parameter pass through K-means clustering algorithms carry out image separation.
Preferably, before the clearing unit, in addition to:Computing unit is retracted, is collected for working as in the shopping cart Commodity amount when reducing, judge that user retracts the commodity, and send prompt message.
A kind of shopping recognition methods and shopping cart identification device that the invention described above provides, shopping is put into by obtaining user The bar code information of in-car commodity, so as to generate shopping list, check that user adds shopping car trader by the shopping list Whether the type and quantity of product are consistent with the commodity on the shopping list, and inconsistent or check checking commodity Commodity can remind user to add the shopping cart after commodity barcode scanning in time not in the shopping list, and pass through institute Shopping cart is stated to carry out self-service barcode scanning to commodity and identify commodity and correspondence valency that user is specifically thrown into the shopping cart Lattice, so as to carry out real-time counting and checkout.Shopping is not added by being effectively prevented from omitting to commodity progress image recognition The commodity of inventory, and the purchase of user is improved because of the time waited in line needed for commodity barcode scanning when efficiently reducing user's checkout Thing efficiency, save personal time.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by embodiment it is required use it is attached Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, therefore be not construed as pair The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, can also be according to this A little accompanying drawings obtain other related accompanying drawings.
Fig. 1 is the structured flowchart of electronic equipment provided in an embodiment of the present invention;
Fig. 2 is a kind of flow chart for shopping recognition methods that first embodiment of the invention provides;
Fig. 3 is a kind of flow chart for shopping recognition methods that second embodiment of the invention provides;
Fig. 4 is a kind of high-level schematic functional block diagram for shopping cart identification device that third embodiment of the invention provides.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is Part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.Therefore, The detailed description of the embodiments of the invention to providing in the accompanying drawings is not intended to limit the model of claimed invention below Enclose, but be merely representative of the selected embodiment of the present invention.Based on the embodiment in the present invention, those of ordinary skill in the art are not having There is the every other embodiment made and obtained under the premise of creative work, belong to the scope of protection of the invention.
As shown in figure 1, the structured flowchart for a kind of electronic equipment provided in an embodiment of the present invention.The electronic equipment 300 Including shopping cart identification device 400, memory 302, storage control 303, processor 304 and Peripheral Interface 305.
The memory 302, storage control 303, processor 304 and 305 each element of Peripheral Interface are direct between each other Or be electrically connected with indirectly, to realize the transmission of data or interaction.For example, these elements can pass through one or more between each other Communication bus or signal wire, which are realized, to be electrically connected with.The shopping cart identification device 400 include it is at least one can be with software or firmware (firmware) form is stored in the memory 302 or is solidificated in the operating system of the electronic equipment 300 Software function module in (operating system, OS).The processor 304 is used to perform what is stored in memory 302 Executable module, such as the software function module or computer program that the shopping cart identification device 400 includes.
Wherein, memory 302 may be, but not limited to, random access memory (Random Access Memory, RAM), read-only storage (Read Only Memory, ROM), programmable read only memory (Programmable Read- Only Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM), electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory, EEPROM) etc..Wherein, memory 302 is used for storage program, and the processor 304 is after execute instruction is received, described in execution Program, the method performed by server 100 that the stream process that foregoing any embodiment of the embodiment of the present invention discloses defines can answer Realized in processor 304, or by processor 304.
Processor 304 is probably a kind of IC chip, has the disposal ability of signal.Above-mentioned processor 304 can To be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processing unit (Network Processor, abbreviation NP) etc.;Can also be digital signal processor (DSP), application specific integrated circuit (ASIC), Ready-made programmable gate array (FPGA) either other PLDs, discrete gate or transistor logic, discrete hard Part component.It can realize or perform disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor Can be microprocessor or any conventional processor etc..
Various input/output devices are coupled to processor 304 and memory 302 by the Peripheral Interface 305.At some In embodiment, Peripheral Interface 305, processor 304 and storage control 303 can be realized in one single chip.Other one In a little examples, they can be realized by independent chip respectively.
Referring to Fig. 2, it is a kind of flow chart for shopping recognition methods that first embodiment of the invention provides.The shopping is known Other method is applied to shopping cart identification device, and the idiographic flow shown in Fig. 2 will be described in detail below.
Step S101, obtains the bar code information for the commodity that user is put into shopping cart, and generates shopping list.
In the present embodiment, the shopping cart is provided with industrial panel computer, barcode scanning module, camera and communication mould Block.The industrial panel computer is used to show shopping list and handles the purchase data of user.
Wherein, the industrial panel computer includes 8 cun of display screen, J1900 processors, 64G solid state hard discs and 4G internal memories. The display screen, the solid state hard disc and the internal memory couple with the processor.
Wherein, the scan module can be that one-dimensional two-dimensional high speed scanner that moral is irrigated or other models are swept Retouch instrument.Here, it is not especially limited.
In the present embodiment, as a kind of application scenarios, the bar of the barcode scanning module acquisition commodity on the shopping cart is passed through Code information, and accessed bar code information is sent to processor and handled, the processor will be accessed The bar code information generates shopping list, and is shown by the display screen.
As a kind of embodiment, user passes through selected commodity installed in the shopping cart when being done shopping On barcode scanning module be scanned, it is raw so as to being handled by the industrial panel computer being pre-installed on the shopping cart Into shopping list, and show the shopping list.
Step S102, judge whether there are the commodity for not scanning bar code in the shopping cart.
As a kind of embodiment, the commodity in shopping cart are gathered in real time by the camera on the shopping cart Image, so as to judge whether the commodity in the shopping cart are consistent with the commodity on shopping list.When inconsistent, described in judgement At least one commodity does not scan bar code in shopping cart.When consistent, judge that the commodity in the shopping cart have been swept Retouch bar code.Specifically, the image of all commodity in the shopping cart is gathered;Based on described image, the shopping cart is identified Interior commodity amount and type of merchandize;Judge whether the type of merchandize and the commodity amount are consistent with the shopping list; If so, judge that the commodity in the shopping cart have scanned bar code;If it is not, judge in the shopping cart have it is at least one Commodity do not scan bar code.
Wherein, in order to identify the commodity amount and type of merchandize in the shopping cart, it is preferable that first judge in described image Commodity image whether occur it is overlapping;If so, carrying out image separation to described image based on image segmentation algorithm, obtain through separation Target image;Obtain the characteristics of image in the target image;Based on described image characteristic query pre-set image database, obtain Take the type of merchandize and commodity amount corresponding to described image feature.
Wherein, in order to carry out image separation, it is preferable that convert the image into gray-scale map;Based on the single of gray level Stochastic variable distributes the intensity level of the pixel of the gray-scale map;The image histogram distribution of gray level of the acquisition amplitude more than 1 Amplitude threshold, the amplitude threshold meets: Wherein, l0Represent that amplitude is big In or equal to 1 gray level, StRepresent gray level l0The summation of appearance;Each gray level image is obtained based on described image histogram Self-adapting window width, the self-adapting window width w meets:Wherein, ltRepresent Amplitude is more than or equal to threshold amplitude T in histogrampGray level sum, α is a constant { α ∈ Z+|1≤α≤lt};It is based on Vertical scanning histogram obtains all peak values that amplitude is more than the amplitude threshold;Based on horizontal sweep histogram to obtain reality Peak grayscale level, the true peak gray level lrMeet:Wherein, liExpression belongs to by window w The amplitude of the grey level range r of definition gray level;Included in gray level and the gray level image based on peak-peak Initiation parameter carries out image separation by K-means clustering algorithms.
Wherein, in order to convert the image into gray-scale map, it is preferable that in gray level image, use the single of gray level Stochastic variable distributes the intensity level of pixel.In the case of gray level image, gray level li is defined as { li ∈ Z+∪0|0≤ li≤255}.Each gray level has the appearance grade of its own in gray level image, its be actually histogram functions value or The density of the gray level.The sum of required block may be calculated:
Wherein,Represent upper limit function;H represents the width of block.In image histogram, the Nogata of 8-bit gray level images Figure includes 256 blocks, and index value is from 0 to 255.Gray-scale map includes has minimum 0 and the intensity for being up to 255 intensity levels respectively Level.So the width h of block be chosen as 1 and gray level maximum be 255, then the total k of block be changed into 256.
In the present embodiment, in order to obtain the characteristics of image in the target image, it is preferable that first by principal component point Analyse (PCA), the gray feature of two kinds of feature extracting method extraction commodity images of linear discriminant analysis (LDA);Secondly, in order that obtaining The colour information of commodity image can be utilized, subchannel spy is then carried out to its chrominance component in rgb space and HSI spaces respectively Sign is extracted and designs three kinds of categorised decision criterions and commodity image is identified;Finally, on the basis using HSI color properties On, commodity identification is carried out using a kind of secondary classification method.Specifically:
(1), the commodity image feature extraction based on principal component analysis and linear discriminant analysis.
Read in commodity storehouse image.Select in commodity storehouse per a part of image construction training sample set X={ X of class commodityi (m, n), m=0,1 ..., M-1;N=0,1 ..., N-1 }, each image Xi(m, n) can be using tabular form as M × N one-dimensional vector;
Calculate overall distribution (covariance) matrix.By formulaObtain training sample set Total population scatter matrix.Wherein K is training sample number, xiFor i-th of training sample vector, μxFor being averaged for all training samples Vector;
Solve the characteristic value and characteristic vector of scatter matrix;
If commodity image shares c classes, the total sample number for participating in training is N, adheres to this c classification separately.ωiClass has NiIndividual sample This.Training sample belongs to ωiThe prior probability of class commodity is
By formulaWithGeneration instruction Practice in the class of sample set, scatter matrix between class;
One group of characteristic vector that most resolution capability is solved using PCA+LDA methods forms transformation matrix.First with PCA methods obtain the reduced order subspace W of training sample total population scatter matrixPCA, then solve matrixCharacteristic vector form WPCA, obtain final transformation matrixThat is commodity figure The reduced order subspace of picture;
Extract training sample feature.Only choose characteristic vector composition reduced order subspace corresponding to the preceding d characteristic value of maximum Td=[a1a2…ad].All training images are projected into the subspace, i.e.,D Wei Te as training sample Sign vector;
Extract test samples feature.Test samples are equally projected to proper subspace TdOn, it is possible to obtain examining sample This feature;In the grader that finally the feature input of test samples is trained, result is identified.
In the present embodiment, the target image refers to after carrying out image separation to described image based on image segmentation algorithm Resulting image.
(2) subchannel feature extraction, is carried out to colored commodity image.
For the training sample set of colored commodity image, first three components of every width coloured image are expressed as arranging The form of vector, then combines all training images of corresponding same components, forms three respective instructions of component Practice collection X1, X2, X3
According to the algorithmic procedure in above-mentioned steps (1), the feature for obtaining three components using PCA or LDA methods respectively is sub Space W1, W2, W3.By each component of training sample respectively to corresponding eigen-subspace projection, three face of training sample are obtained The respective characteristic vector of colouring component;
Equally, three color components of each test samples are also projected into each self-corresponding proper subspace, examined Test the feature of three components of sample;
The design of categorised decision criterion.Average distance method, nearest neighbor classifier is extended in colored commodity image identification, Nearest neighbor classifier is current relatively direct also more more commonly used sorting technique, and its basic thought is selection and test samples distance Classification of the classification of nearest training sample as the sample;K nearest neighbor algorithm (K-Nearest Neighbor Algorithm), three respective recognition results of color component of sample are respectively obtained by nearest neighbor classifier, according to ballot rule The final affiliation classifier of sample to be identified is therefrom selected for different situations;Centre distance method, calculate sample to be identified and instruction " centre distance " for practicing each classification in sample obtains the recognition result of each color component, differentiates further according to criterion to be identified Commodity image generic.
(3), the commodity image identification based on secondary classification method.
Extract the feature of commodity image training sample tri- passages of HSI respectively using PCA or LDA methods, form HSI features Vector, obtain the color property of training sample.The HSI color properties of same extraction test samples are as commodity original feature;
Using training sample feature, super ellipsoids neutral net is trained, obtained network parameter is as training Super ellipsoids neural network classifier;
Using training sample feature, error correction SVM (SVMs) grader is trained, obtains error correction svm classifier The parameter of device;
Sample characteristics are inputted in super ellipsoids neutral net and carry out the first subseries, the sample for result can be identified This, it is not necessary to the second subseries is carried out, directly using the result as final recognition result;
For the sample for running into rejection in the first subseries or knowing more, then the is carried out again by error correction SVM classifier Secondary classification, final recognition result is obtained, so as to complete the Classification and Identification to the sample, and extract bar code information.
Wherein, in the present embodiment, in order to obtain the value volume and range of product of commodity, it is preferable that separate and scheme in commodity image As identification during the commodity image after separation is counted, and according to the bar code that image recognition result is returned from And obtain type of merchandize and commodity price.
Step S103, if so, obtaining the total price of all commodity in the shopping cart.
When judging that the commodity in the shopping cart are consistent with the commodity on the shopping list, user can be based on described Shopping list is settled accounts, and can continue to buy commodity.
In the present embodiment, when judging that at least one commodity does not scan bar code in the shopping cart, institute is controlled The brake for stating shopping cart is braked, so that user can not promote the shopping cart.For example, commodity are identified in shopping cart During with counting, find to check without such commodity, shopping cart in shopping list.
Referring to Fig. 3, it is the flow chart for the shopping recognition methods that second embodiment of the invention provides.The shopping identification side Method is applied to shopping cart identification device, and the idiographic flow shown in Fig. 3 will be described in detail below.
Step S201, obtains the bar code information for the commodity that user is put into shopping cart, and generates shopping list.
Step S202, judge whether there are the commodity for not scanning bar code in the shopping cart.
Step S201 and step S202 embodiment refer to step corresponding in first embodiment, here, Repeat no more.
Step S203, when collecting the reduction of the commodity amount in the shopping cart, judge that user retracts the commodity, and Send prompt message.
As a kind of embodiment, when the commodity amount is reduced, judge user by the merchandise return arrival of shopping cart Frame is either put into collection box, i.e. user is retracted the commodity that need not be bought.For example, user directly takes from shopping cart Go out, i.e., determine whether that commodity take out out of shopping cart by the image collected, for example, being sentenced by judging commodity amount It is disconnected whether to there are commodity to be taken out easily by the user.Shelf are put back to after swipe shape code, shopping cart prompting subtracts commodity;Another way is to settle accounts Place is put into collection box after the commodity for being not desired to purchase are taken out into swipe shape code, and shopping cart prompting subtracts commodity.For example, preset when figure As identification is when taking out commodity and swipe shape code out of shopping cart, to be judged to subtracting commodity.
Step S204, if so, obtaining the total price of all commodity in the shopping cart.
Step S204 embodiment refer to step corresponding in first embodiment, here, repeating no more.
Referring to Fig. 4, it is a kind of high-level schematic functional block diagram for shopping cart identification device that third embodiment of the invention provides. The shopping cart identification device 400 includes:Data capture unit 410, judging unit 420, retract computing unit 430 and advice of settlement Member 440.
Data capture unit 410, the bar code information for the commodity being put into for obtaining user in shopping cart, and generate shopping Inventory.
Judging unit 420, for judging whether there are the commodity for not scanning bar code in the shopping cart.
Wherein, the judging unit 420 includes:Gather subelement, identification subelement, judgment sub-unit, the first result list Member and the second result unit.
The collection subelement, for gathering the image of all commodity in the shopping cart.
The identification subelement, for based on described image, identifying the commodity amount and type of merchandize in the shopping cart.
Wherein, the identification subelement includes:Judging submodule, image procossing submodule, acquisition submodule and inquiry Module.
The judging submodule, for judging it is overlapping whether the commodity image in described image occurs.
Described image handles submodule, for if so, based on image segmentation algorithm to described image progress image separation, obtaining Take separated target image.
Wherein, described image processing submodule is specifically used for:Convert the image into gray-scale map;List based on gray level Individual stochastic variable distributes the intensity level of the pixel of the gray-scale map;The image histogram point of gray level of the acquisition amplitude more than 1 The amplitude threshold of cloth, the amplitude threshold meet: Wherein, l0Represent amplitude Gray level more than or equal to 1, StRepresent gray level l0The summation of appearance;Each gray-scale map is obtained based on described image histogram The self-adapting window width of picture, the self-adapting window width w meet:Wherein, ltRepresent Amplitude is more than or equal to threshold amplitude T in histogrampGray level sum, α is a constant { α ∈ Z+|1≤α≤lt};Base All peak values of the amplitude more than the amplitude threshold are obtained in vertical scanning histogram;Based on horizontal sweep histogram to obtain reality Border peak grayscale level, the true peak gray level lrMeet:Wherein, liExpression belongs to by window The amplitude of the gray level for the grey level range r that w is defined;Included in gray level and the gray level image based on peak-peak Initiation parameter carries out image separation by K-means clustering algorithms.
The acquisition submodule, for obtaining the characteristics of image in the target image.
The inquiry submodule, for based on described image characteristic query pre-set image database, it is special to obtain described image The corresponding type of merchandize of sign and commodity amount.
The judgment sub-unit, for judge the type of merchandize and the commodity amount whether with the shopping list one Cause.
The first result unit, for if so, judging that the commodity in the shopping cart have scanned bar code.
The second result unit, for if it is not, judging there are at least one commodity not have scan stripes in the shopping cart Shape code.
Computing unit 430 is retracted, for when collecting the reduction of the commodity amount in the shopping cart, judging that user retracts The commodity, and send prompt message.
Clearing unit 440, for if so, obtaining the total price of all commodity in the shopping cart.
In summary, the present invention provides a kind of shopping recognition methods and shopping cart identification device, is put into by obtaining user The bar code information of commodity in shopping cart, so as to generate shopping list, check that user adds shopping by the shopping list Whether the type and quantity of car trader's product consistent with the commodity on the shopping list, and check commodity it is inconsistent or inspection Finding commodity can remind user to add the shopping cart after commodity barcode scanning in time not in the shopping list, and lead to The shopping cart is crossed to carry out self-service barcode scanning to commodity and identify commodity that user specifically thrown into the shopping cart and right Dutiable value, so as to carry out real-time counting and checkout.Do not added by efficiently avoid omission to commodity progress image recognition Because of the time waited in line needed for commodity barcode scanning when entering the commodity of shopping list, and efficiently reducing user's checkout, improve and use The shopping efficiency at family, save personal time.
In several embodiments provided herein, it should be understood that disclosed apparatus and method, can also pass through Other modes are realized.Device embodiment described above is only schematical, for example, flow chart and block diagram in accompanying drawing Show the device of multiple embodiments according to the present invention, method and computer program product architectural framework in the cards, Function and operation.At this point, each square frame in flow chart or block diagram can represent the one of a module, program segment or code Part, a part for the module, program segment or code include one or more and are used to realize holding for defined logic function Row instruction.It should also be noted that at some as in the implementation replaced, the function that is marked in square frame can also with different from The order marked in accompanying drawing occurs.For example, two continuous square frames can essentially perform substantially in parallel, they are sometimes It can perform in the opposite order, this is depending on involved function.It is it is also noted that every in block diagram and/or flow chart The combination of individual square frame and block diagram and/or the square frame in flow chart, function or the special base of action as defined in performing can be used Realize, or can be realized with the combination of specialized hardware and computer instruction in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate to form an independent portion Point or modules individualism, can also two or more modules be integrated to form an independent part.
If the function is realized in the form of software function module and is used as independent production marketing or in use, can be with It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words The part to be contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter Calculation machine software product is stored in a storage medium, including some instructions are causing a computer equipment (can be People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the present invention. And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access Memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.Need It is noted that herein, such as first and second or the like relational terms are used merely to an entity or operation Made a distinction with another entity or operation, and not necessarily require or imply these entities or exist between operating any this Actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to nonexcludability Comprising so that process, method, article or equipment including a series of elements not only include those key elements, but also wrapping Include the other element being not expressly set out, or also include for this process, method, article or equipment intrinsic want Element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that wanted including described Other identical element also be present in the process of element, method, article or equipment.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies Change, equivalent substitution, improvement etc., should be included in the scope of the protection.It should be noted that:Similar label and letter exists Similar terms is represented in following accompanying drawing, therefore, once being defined in a certain Xiang Yi accompanying drawing, is then not required in subsequent accompanying drawing It is further defined and explained.

Claims (10)

1. one kind shopping recognition methods, applied to shopping cart identification device, it is characterised in that including:
The bar code information for the commodity that user is put into shopping cart is obtained, and generates shopping list;
Judge whether there are the commodity for not scanning bar code in the shopping cart;
If so, obtain the total price of all commodity in the shopping cart.
2. according to the method for claim 1, it is characterised in that it is described judge whether to have in the shopping cart do not scan bar shaped The commodity of code, including:
Gather the image of all commodity in the shopping cart;
Based on described image, the commodity amount and type of merchandize in the shopping cart are identified;
Judge whether the type of merchandize and the commodity amount are consistent with the shopping list;
If so, judge that the commodity in the shopping cart have scanned bar code;
If it is not, judge there are at least one commodity not scan bar code in the shopping cart.
3. according to the method for claim 2, it is characterised in that it is described to be based on described image, identify in the shopping cart Commodity amount and type of merchandize, including:
It is overlapping to judge whether the commodity image in described image occurs;
If so, carrying out image separation to described image based on image segmentation algorithm, separated target image is obtained;
Obtain the characteristics of image in the target image;
Based on described image characteristic query pre-set image database, the type of merchandize corresponding to described image feature and business are obtained Product quantity.
4. according to the method for claim 3, it is characterised in that described that figure is carried out to described image based on image segmentation algorithm As separation, including:
Convert the image into gray-scale map;
Single stochastic variable based on gray level distributes the intensity level of the pixel of the gray-scale map;
The amplitude threshold of the image histogram distribution of gray level of the acquisition amplitude more than 1, the amplitude threshold meet:
<mrow> <msub> <mi>T</mi> <mi>p</mi> </msub> <mo>=</mo> <mrow> <mo>(</mo> <mfrac> <msub> <mi>S</mi> <mi>t</mi> </msub> <msub> <mi>l</mi> <mn>0</mn> </msub> </mfrac> <mo>)</mo> </mrow> <mo>,</mo> <msub> <mi>S</mi> <mi>t</mi> </msub> <mo>=</mo> <munder> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>&amp;Element;</mo> <msub> <mi>l</mi> <mn>0</mn> </msub> </mrow> </munder> <msub> <mi>a</mi> <msub> <mi>l</mi> <mi>i</mi> </msub> </msub> <mo>,</mo> <msub> <mi>l</mi> <mn>0</mn> </msub> <mo>=</mo> <msubsup> <mrow> <mo>(</mo> <msub> <mi>a</mi> <msub> <mi>l</mi> <mi>i</mi> </msub> </msub> <mo>&amp;GreaterEqual;</mo> <mn>1</mn> <mo>)</mo> </mrow> <mrow> <mi>i</mi> <mo>=</mo> <mn>0</mn> </mrow> <mn>255</mn> </msubsup> <mo>,</mo> </mrow>
Wherein, l0Represent the gray level that amplitude is more than or equal to 1, StRepresent gray level l0The summation of appearance;
The self-adapting window width of each gray level image is obtained based on described image histogram, the self-adapting window width w expires Foot:
<mrow> <msub> <mi>l</mi> <mi>t</mi> </msub> <mo>=</mo> <msubsup> <mrow> <mo>(</mo> <msub> <mi>a</mi> <msub> <mi>l</mi> <mi>i</mi> </msub> </msub> <mo>&amp;GreaterEqual;</mo> <msub> <mi>T</mi> <mi>p</mi> </msub> <mo>)</mo> </mrow> <mrow> <mi>i</mi> <mo>=</mo> <mn>0</mn> </mrow> <mn>255</mn> </msubsup> <mo>,</mo> </mrow>
Wherein, ltRepresent that amplitude is more than or equal to threshold amplitude T in histogrampGray level sum, α is a constant { α ∈ Z+|1≤α≤lt};
All peak values of the amplitude more than the amplitude threshold are obtained based on vertical scanning histogram;
Based on horizontal sweep histogram to obtain true peak gray level, the true peak gray level lrMeet:
<mrow> <msub> <mi>l</mi> <mi>r</mi> </msub> <mo>=</mo> <mrow> <mo>(</mo> <msub> <mi>a</mi> <msub> <mi>l</mi> <mi>p</mi> </msub> </msub> <mo>&amp;GreaterEqual;</mo> <msub> <mi>a</mi> <msub> <mi>l</mi> <mi>i</mi> </msub> </msub> <mo>)</mo> </mrow> <mo>,</mo> <mo>&amp;ForAll;</mo> <msub> <mi>a</mi> <msub> <mi>l</mi> <mi>i</mi> </msub> </msub> <mo>&amp;Element;</mo> <mi>r</mi> <mo>,</mo> </mrow>
Wherein, liRepresent the amplitude for belonging to the gray level by the window w grey level range r defined;
Initiation parameter included in gray level and the gray level image based on peak-peak is clustered by K-means to be calculated Method carries out image separation.
5. according to the method for claim 1, it is characterised in that described if so, obtaining all business in the shopping cart The total price of product, also includes before:
When collecting the reduction of the commodity amount in the shopping cart, judge that user retracts the commodity, and send prompt message.
A kind of 6. shopping cart identification device, it is characterised in that including:
Data capture unit, the bar code information for the commodity being put into for obtaining user in shopping cart, and generate shopping list;
Judging unit, for judging whether there are the commodity for not scanning bar code in the shopping cart;
Clearing unit, for if so, obtaining the total price of all commodity in the shopping cart.
7. device according to claim 6, it is characterised in that the judging unit includes:
Subelement is gathered, for gathering the image of all commodity in the shopping cart;
Subelement is identified, for based on described image, identifying the commodity amount and type of merchandize in the shopping cart;
Judgment sub-unit, for judging whether the type of merchandize and the commodity amount are consistent with the shopping list;
First result unit, for if so, judging that the commodity in the shopping cart have scanned bar code;
Second result unit, for if it is not, judging there are at least one commodity not scan bar code in the shopping cart.
8. device according to claim 7, it is characterised in that the identification subelement includes:
Judging submodule, for judging it is overlapping whether the commodity image in described image occurs;
Image procossing submodule, for if so, based on image segmentation algorithm to described image progress image separation, obtaining through separation Target image;
Acquisition submodule, for obtaining the characteristics of image in the target image;
Submodule is inquired about, for based on described image characteristic query pre-set image database, obtaining corresponding to described image feature Type of merchandize and commodity amount.
9. device according to claim 8, it is characterised in that described image processing submodule is specifically used for:
Convert the image into gray-scale map;
Single stochastic variable based on gray level distributes the intensity level of the pixel of the gray-scale map;
The amplitude threshold of the image histogram distribution of gray level of the acquisition amplitude more than 1, the amplitude threshold meet:
<mrow> <msub> <mi>T</mi> <mi>p</mi> </msub> <mo>=</mo> <mrow> <mo>(</mo> <mfrac> <msub> <mi>S</mi> <mi>t</mi> </msub> <msub> <mi>l</mi> <mn>0</mn> </msub> </mfrac> <mo>)</mo> </mrow> <mo>,</mo> <msub> <mi>S</mi> <mi>t</mi> </msub> <mo>=</mo> <munder> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>&amp;Element;</mo> <msub> <mi>l</mi> <mn>0</mn> </msub> </mrow> </munder> <msub> <mi>a</mi> <msub> <mi>l</mi> <mi>i</mi> </msub> </msub> <mo>,</mo> <msub> <mi>l</mi> <mn>0</mn> </msub> <mo>=</mo> <msubsup> <mrow> <mo>(</mo> <msub> <mi>a</mi> <msub> <mi>l</mi> <mi>i</mi> </msub> </msub> <mo>&amp;GreaterEqual;</mo> <mn>1</mn> <mo>)</mo> </mrow> <mrow> <mi>i</mi> <mo>=</mo> <mn>0</mn> </mrow> <mn>255</mn> </msubsup> <mo>,</mo> </mrow>
Wherein, l0Represent the gray level that amplitude is more than or equal to 1, StRepresent gray level l0The summation of appearance;
The self-adapting window width of each gray level image is obtained based on described image histogram, the self-adapting window width w expires Foot:
<mrow> <msub> <mi>l</mi> <mi>t</mi> </msub> <mo>=</mo> <msubsup> <mrow> <mo>(</mo> <msub> <mi>a</mi> <msub> <mi>l</mi> <mi>i</mi> </msub> </msub> <mo>&amp;GreaterEqual;</mo> <msub> <mi>T</mi> <mi>p</mi> </msub> <mo>)</mo> </mrow> <mrow> <mi>i</mi> <mo>=</mo> <mn>0</mn> </mrow> <mn>255</mn> </msubsup> <mo>,</mo> </mrow>
Wherein, ltRepresent that amplitude is more than or equal to threshold amplitude T in histogrampGray level sum, α is a constant { α ∈ Z+|1≤α≤lt};
All peak values of the amplitude more than the amplitude threshold are obtained based on vertical scanning histogram;
Based on horizontal sweep histogram to obtain true peak gray level, the true peak gray level lrMeet:
<mrow> <msub> <mi>l</mi> <mi>r</mi> </msub> <mo>=</mo> <mrow> <mo>(</mo> <msub> <mi>a</mi> <msub> <mi>l</mi> <mi>p</mi> </msub> </msub> <mo>&amp;GreaterEqual;</mo> <msub> <mi>a</mi> <msub> <mi>l</mi> <mi>i</mi> </msub> </msub> <mo>)</mo> </mrow> <mo>,</mo> <mo>&amp;ForAll;</mo> <msub> <mi>a</mi> <msub> <mi>l</mi> <mi>i</mi> </msub> </msub> <mo>&amp;Element;</mo> <mi>r</mi> <mo>,</mo> </mrow>
Wherein, liRepresent the amplitude for belonging to the gray level by the window w grey level range r defined;
Initiation parameter included in gray level and the gray level image based on peak-peak is clustered by K-means to be calculated Method carries out image separation.
10. device according to claim 6, it is characterised in that before the clearing unit, in addition to:
Computing unit is retracted, for when collecting the reduction of the commodity amount in the shopping cart, judging that user retracts the business Product, and send prompt message.
CN201710811178.8A 2017-09-11 2017-09-11 One kind shopping recognition methods and shopping cart identification device Pending CN107610379A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710811178.8A CN107610379A (en) 2017-09-11 2017-09-11 One kind shopping recognition methods and shopping cart identification device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710811178.8A CN107610379A (en) 2017-09-11 2017-09-11 One kind shopping recognition methods and shopping cart identification device

Publications (1)

Publication Number Publication Date
CN107610379A true CN107610379A (en) 2018-01-19

Family

ID=61062132

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710811178.8A Pending CN107610379A (en) 2017-09-11 2017-09-11 One kind shopping recognition methods and shopping cart identification device

Country Status (1)

Country Link
CN (1) CN107610379A (en)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108242061A (en) * 2018-02-11 2018-07-03 南京亿猫信息技术有限公司 A kind of supermarket shopping car hard recognition method based on Sobel operators
CN108520280A (en) * 2018-04-12 2018-09-11 河南机电职业学院 A kind of bulk commodity charge system based on machine vision
CN108682091A (en) * 2018-05-21 2018-10-19 深圳码隆科技有限公司 A kind of shopping settlement method, device and user terminal
CN108921645A (en) * 2018-06-07 2018-11-30 深圳码隆科技有限公司 A kind of commodity purchasing determination method, device and user terminal
CN108921048A (en) * 2018-06-14 2018-11-30 深圳码隆科技有限公司 A kind of shopping settlement method, device and user terminal
CN109271920A (en) * 2018-09-12 2019-01-25 上海了物网络科技有限公司 The vision system and method and medium for supporting article to identify
CN109353398A (en) * 2018-09-20 2019-02-19 北京旷视科技有限公司 Commodity recognition method, device and system and storage medium and shopping cart
CN109977251A (en) * 2019-03-05 2019-07-05 武汉摩小超科技有限公司 A method of building identifies commodity based on RGB histogram feature
WO2020187036A1 (en) * 2019-03-15 2020-09-24 南京亿猫信息技术有限公司 Shopping tool-based anti-fraud system
CN112116121A (en) * 2020-07-29 2020-12-22 大众问问(北京)信息科技有限公司 Driving route recommendation method and device, electronic device and storage medium
CN112184104A (en) * 2020-09-18 2021-01-05 安徽三禾一信息科技有限公司 Material stacking method for storage
CN112215311A (en) * 2020-09-07 2021-01-12 上海原能细胞生物低温设备有限公司 Sample warehousing method and device, computer equipment and storage medium
CN117422937A (en) * 2023-12-18 2024-01-19 成都阿加犀智能科技有限公司 Intelligent shopping cart state identification method, device, equipment and storage medium

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102184405A (en) * 2011-04-19 2011-09-14 清华大学 Image acquisition-analysis method
CN202806824U (en) * 2012-04-25 2013-03-20 蒋建民 Intelligent shopping cart of shopping mall
CN106097077A (en) * 2016-06-23 2016-11-09 南京邮电大学 A kind of self-help payment smart shopper system
CN206031442U (en) * 2016-08-26 2017-03-22 北京乐动卓越科技有限公司 Take magnetic stripe scanning function's self -service shopping cart
CN106608275A (en) * 2015-10-27 2017-05-03 唐超(北京)科技有限公司 Self-service checkout shopping cart
CN206179134U (en) * 2016-09-21 2017-05-17 深圳市泛海三江科技发展有限公司 Discuss outstandingly intelligent ability anti -theft system
CN106781014A (en) * 2017-01-24 2017-05-31 广州市蚁道互联网有限公司 Automatic vending machine and its operation method
CN107038822A (en) * 2017-03-27 2017-08-11 杭州赛狐科技有限公司 A kind of self-service POS and method

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102184405A (en) * 2011-04-19 2011-09-14 清华大学 Image acquisition-analysis method
CN202806824U (en) * 2012-04-25 2013-03-20 蒋建民 Intelligent shopping cart of shopping mall
CN106608275A (en) * 2015-10-27 2017-05-03 唐超(北京)科技有限公司 Self-service checkout shopping cart
CN106097077A (en) * 2016-06-23 2016-11-09 南京邮电大学 A kind of self-help payment smart shopper system
CN206031442U (en) * 2016-08-26 2017-03-22 北京乐动卓越科技有限公司 Take magnetic stripe scanning function's self -service shopping cart
CN206179134U (en) * 2016-09-21 2017-05-17 深圳市泛海三江科技发展有限公司 Discuss outstandingly intelligent ability anti -theft system
CN106781014A (en) * 2017-01-24 2017-05-31 广州市蚁道互联网有限公司 Automatic vending machine and its operation method
CN107038822A (en) * 2017-03-27 2017-08-11 杭州赛狐科技有限公司 A kind of self-service POS and method

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108242061B (en) * 2018-02-11 2022-04-08 南京亿猫信息技术有限公司 Supermarket shopping cart hand identification method based on Sobel operator
CN108242061A (en) * 2018-02-11 2018-07-03 南京亿猫信息技术有限公司 A kind of supermarket shopping car hard recognition method based on Sobel operators
CN108520280A (en) * 2018-04-12 2018-09-11 河南机电职业学院 A kind of bulk commodity charge system based on machine vision
CN108682091A (en) * 2018-05-21 2018-10-19 深圳码隆科技有限公司 A kind of shopping settlement method, device and user terminal
CN108921645A (en) * 2018-06-07 2018-11-30 深圳码隆科技有限公司 A kind of commodity purchasing determination method, device and user terminal
CN108921048A (en) * 2018-06-14 2018-11-30 深圳码隆科技有限公司 A kind of shopping settlement method, device and user terminal
CN109271920A (en) * 2018-09-12 2019-01-25 上海了物网络科技有限公司 The vision system and method and medium for supporting article to identify
CN109353398A (en) * 2018-09-20 2019-02-19 北京旷视科技有限公司 Commodity recognition method, device and system and storage medium and shopping cart
CN109353398B (en) * 2018-09-20 2020-11-10 北京旷视科技有限公司 Commodity identification method, device and system, storage medium and shopping cart
CN109977251A (en) * 2019-03-05 2019-07-05 武汉摩小超科技有限公司 A method of building identifies commodity based on RGB histogram feature
WO2020187036A1 (en) * 2019-03-15 2020-09-24 南京亿猫信息技术有限公司 Shopping tool-based anti-fraud system
CN112116121A (en) * 2020-07-29 2020-12-22 大众问问(北京)信息科技有限公司 Driving route recommendation method and device, electronic device and storage medium
CN112215311A (en) * 2020-09-07 2021-01-12 上海原能细胞生物低温设备有限公司 Sample warehousing method and device, computer equipment and storage medium
CN112184104A (en) * 2020-09-18 2021-01-05 安徽三禾一信息科技有限公司 Material stacking method for storage
CN117422937A (en) * 2023-12-18 2024-01-19 成都阿加犀智能科技有限公司 Intelligent shopping cart state identification method, device, equipment and storage medium
CN117422937B (en) * 2023-12-18 2024-03-15 成都阿加犀智能科技有限公司 Intelligent shopping cart state identification method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN107610379A (en) One kind shopping recognition methods and shopping cart identification device
CN108491799B (en) Intelligent sales counter commodity management method and system based on image recognition
DE112011102294T5 (en) Optimizing the detection of human activity from video material
CN108304816B (en) Identity recognition method and device, storage medium and electronic equipment
CN106651834A (en) Method and device for evaluating quality of substation equipment infrared thermal image with no reference image
KR102295660B1 (en) System for providing internet of things device sharing service for one-person households
US20200104748A1 (en) Image processing for item recognition
Lei et al. Infrared pedestrian segmentation algorithm based on the two-dimensional Kaniadakis entropy thresholding
KR20230060452A (en) Action determination program, action determination method, and action determination device
Sahoo Automatic recognition of Indian vehicles license plates using machine learning approaches
CN111310531B (en) Image classification method, device, computer equipment and storage medium
CN115018513A (en) Data inspection method, device, equipment and storage medium
Tao et al. Object detection-based license plate localization and recognition in complex environments
Huang et al. Cost-sensitive sparse linear regression for crowd counting with imbalanced training data
CN117523748A (en) Checkout commodity identification system for financial payment
Jurgovsky Context-aware credit card fraud detection
CN110472680B (en) Object classification method, device and computer-readable storage medium
CN110874734A (en) Dynamic two-dimensional code generation method and device
CN110874733A (en) Passive code scanning payment method and device supporting external equipment
Priyanka et al. Classification approach based customer prediction analysis for loan preferences of customers
US20240005292A1 (en) Self-service checkout terminal, and method
JP7412821B2 (en) information processing system
CN111091367A (en) Open type quick payment method and device
Behera et al. ResNet101-SVM: Hybrid convolutional neural network for citrus fruits classification
CN111091368A (en) Closed type quick payment method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20180119